Comparer des méthodes

	Apprentissage par transfert pour la synthèse de texte	Apprentissage par transfert avec reconnaissance d'entités nommées
Domaine	Apprentissage profond	Apprentissage profond
Famille	Machine learning	Machine learning
Année d'origine	2019–2020	2010 / 2019
Auteur d'origine	Raffel et al. (T5); Lewis et al. (BART)	Pan & Yang (transfer learning); Devlin et al. (BERT-based NER fine-tuning)
Type	Transfer learning applied to sequence-to-sequence summarization	Supervised sequence labeling via pretrained encoder fine-tuning
Source fondatrice	Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2020). Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of Machine Learning Research, 21(140), 1–67.	Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of NAACL-HLT 2019 (pp. 4171–4186). Association for Computational Linguistics.
Alias	pretrained summarization model, fine-tuned summarization, TL-summarization, neural abstractive summarization via transfer learning	TL-NER, Fine-Tuned NER, Pretrained Model NER, BERT NER
Apparentées	4	5
Résumé	Transfer Learning with Text Summarization adapts a large language model pre-trained on broad text corpora — such as T5, BART, or PEGASUS — to the task of condensing documents into shorter, coherent summaries. By reusing learned linguistic knowledge and fine-tuning on domain-specific pairs of source documents and reference summaries, this approach achieves strong summarization quality with modest labeled data requirements.	Transfer Learning with Named Entity Recognition (NER) adapts a large pretrained language model — such as BERT, RoBERTa, or a domain-specific encoder — to the task of identifying and classifying named entities (persons, locations, organizations, dates, etc.) in text. By reusing rich linguistic representations learned from massive corpora, this approach requires only modest labeled NER data while achieving state-of-the-art span detection and classification accuracy.